@@ -135,20 +135,20 @@ adversarial training losses). The training loop itself is defined in
...
@@ -135,20 +135,20 @@ adversarial training losses). The training loop itself is defined in
### Command-Line Flags
### Command-Line Flags
Flags related to distributed training and the training loop itself are defined
Flags related to distributed training and the training loop itself are defined
in [`train_utils.py`](https://github.com/tensorflow/models/tree/master/adversarial_text/train_utils.py).
in [`train_utils.py`](https://github.com/tensorflow/models/tree/master/research/adversarial_text/train_utils.py).
Flags related to model hyperparameters are defined in [`graphs.py`](https://github.com/tensorflow/models/tree/master/adversarial_text/graphs.py).
Flags related to model hyperparameters are defined in [`graphs.py`](https://github.com/tensorflow/models/tree/master/research/adversarial_text/graphs.py).
Flags related to adversarial training are defined in [`adversarial_losses.py`](https://github.com/tensorflow/models/tree/master/adversarial_text/adversarial_losses.py).
Flags related to adversarial training are defined in [`adversarial_losses.py`](https://github.com/tensorflow/models/tree/master/research/adversarial_text/adversarial_losses.py).
Flags particular to each job are defined in the main binary files.
Flags particular to each job are defined in the main binary files.
* Data generation: [`gen_data.py`](https://github.com/tensorflow/models/tree/master/adversarial_text/data/gen_data.py)
* Data generation: [`gen_data.py`](https://github.com/tensorflow/models/tree/master/research/adversarial_text/data/gen_data.py)
Command-line flags defined in [`document_generators.py`](https://github.com/tensorflow/models/tree/master/adversarial_text/data/document_generators.py)
Command-line flags defined in [`document_generators.py`](https://github.com/tensorflow/models/tree/master/research/adversarial_text/data/document_generators.py)
module. E.g., create a file datasets/newtextdataset.py:
module. E.g., create a file datasets/newtextdataset.py:
```
```
import fsns
import fsns
...
@@ -151,8 +151,8 @@ To learn how to store a data in the FSNS
...
@@ -151,8 +151,8 @@ To learn how to store a data in the FSNS
- labels: ground truth label ids, shape=[batch_size x seq_length];
- labels: ground truth label ids, shape=[batch_size x seq_length];
- labels_one_hot: labels in one-hot encoding, shape [batch_size x seq_length x num_char_classes];
- labels_one_hot: labels in one-hot encoding, shape [batch_size x seq_length x num_char_classes];
Refer to [python/data_provider.py](https://github.com/tensorflow/models/blob/master/attention_ocr/python/data_provider.py#L33)
Refer to [python/data_provider.py](https://github.com/tensorflow/models/blob/master/research/attention_ocr/python/data_provider.py#L33)
for more details. You can use [python/datasets/fsns.py](https://github.com/tensorflow/models/blob/master/attention_ocr/python/datasets/fsns.py)
for more details. You can use [python/datasets/fsns.py](https://github.com/tensorflow/models/blob/master/research/attention_ocr/python/datasets/fsns.py)
as the example.
as the example.
## How to use a pre-trained model
## How to use a pre-trained model
...
@@ -164,14 +164,14 @@ The recommended way is to use the [Serving infrastructure][serving].
...
@@ -164,14 +164,14 @@ The recommended way is to use the [Serving infrastructure][serving].
Alternatively you can:
Alternatively you can:
1. define a placeholder for images (or use directly an numpy array)
1. define a placeholder for images (or use directly an numpy array)
2.[create a graph ](https://github.com/tensorflow/models/blob/master/attention_ocr/python/eval.py#L60)
2.[create a graph ](https://github.com/tensorflow/models/blob/master/research/attention_ocr/python/eval.py#L60)
**NOTE**: For the most part, you will find a newer version of this code at [models/slim](https://github.com/tensorflow/models/tree/master/slim). In particular:
**NOTE**: For the most part, you will find a newer version of this code at [models/research/slim](https://github.com/tensorflow/models/tree/master/research/slim). In particular:
*`inception_train.py` and `imagenet_train.py` should no longer be used. The slim editions for running on multiple GPUs are the current best examples.
*`inception_train.py` and `imagenet_train.py` should no longer be used. The slim editions for running on multiple GPUs are the current best examples.
*`inception_distributed_train.py` and `imagenet_distributed_train.py` are still valid examples of distributed training.
*`inception_distributed_train.py` and `imagenet_distributed_train.py` are still valid examples of distributed training.
"Welcome to the object detection inference walkthrough! This notebook will walk you step by step through the process of using a pre-trained model to detect objects in an image. Make sure to follow the [installation instructions](https://github.com/tensorflow/models/blob/master/object_detection/g3doc/installation.md) before you start."
"Welcome to the object detection inference walkthrough! This notebook will walk you step by step through the process of using a pre-trained model to detect objects in an image. Make sure to follow the [installation instructions](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md) before you start."
]
]
},
},
{
{
...
@@ -96,7 +96,7 @@
...
@@ -96,7 +96,7 @@
"\n",
"\n",
"Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file. \n",
"Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file. \n",
"\n",
"\n",
"By default we use an \"SSD with Mobilenet\" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies."
"By default we use an \"SSD with Mobilenet\" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies."
"python -c \"import tensorflow.contrib.slim as slim; eval = slim.evaluation.evaluate_once\"\n",
"python -c \"import tensorflow.contrib.slim as slim; eval = slim.evaluation.evaluate_once\"\n",
"```\n",
"```\n",
"\n",
"\n",
"Although, to use TF-Slim for image classification (as we do in this notebook), you also have to install the TF-Slim image models library from [here](https://github.com/tensorflow/models/tree/master/slim). Let's suppose you install this into a directory called TF_MODELS. Then you should change directory to TF_MODELS/slim **before** running this notebook, so that these files are in your python path.\n",
"Although, to use TF-Slim for image classification (as we do in this notebook), you also have to install the TF-Slim image models library from [here](https://github.com/tensorflow/models/tree/master/research/slim). Let's suppose you install this into a directory called TF_MODELS. Then you should change directory to TF_MODELS/research/slim **before** running this notebook, so that these files are in your python path.\n",
"\n",
"\n",
"To check you've got these two steps to work, just execute the cell below. If it complains about unknown modules, restart the notebook after moving to the TF-Slim models directory.\n"
"To check you've got these two steps to work, just execute the cell below. If it complains about unknown modules, restart the notebook after moving to the TF-Slim models directory.\n"
]
]
...
@@ -757,7 +757,7 @@
...
@@ -757,7 +757,7 @@
"<a id='Pretrained'></a>\n",
"<a id='Pretrained'></a>\n",
"\n",
"\n",
"Neural nets work best when they have many parameters, making them very flexible function approximators.\n",
"Neural nets work best when they have many parameters, making them very flexible function approximators.\n",
"However, this means they must be trained on big datasets. Since this process is slow, we provide various pre-trained models - see the list [here](https://github.com/tensorflow/models/tree/master/slim#pre-trained-models).\n",
"However, this means they must be trained on big datasets. Since this process is slow, we provide various pre-trained models - see the list [here](https://github.com/tensorflow/models/tree/master/research/slim#pre-trained-models).\n",
"\n",
"\n",
"\n",
"\n",
"You can either use these models as-is, or you can perform \"surgery\" on them, to modify them for some other task. For example, it is common to \"chop off\" the final pre-softmax layer, and replace it with a new set of weights corresponding to some new set of labels. You can then quickly fine tune the new model on a small new dataset. We illustrate this below, using inception-v1 as the base model. While models like Inception V3 are more powerful, Inception V1 is used for speed purposes.\n",
"You can either use these models as-is, or you can perform \"surgery\" on them, to modify them for some other task. For example, it is common to \"chop off\" the final pre-softmax layer, and replace it with a new set of weights corresponding to some new set of labels. You can then quickly fine tune the new model on a small new dataset. We illustrate this below, using inception-v1 as the base model. While models like Inception V3 are more powerful, Inception V1 is used for speed purposes.\n",
